Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3215 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1982. Min Range: -2.1982

Max Act: 2.1982. Min Act: -0.0000

Data Index: 264952 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 2.1982. Min Range: -2.1982

Max Act: 2.1580. Min Act: -0.0000

Data Index: 403521 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 2.1982. Min Range: -2.1982

Max Act: 2.0254. Min Act: -0.0000

Data Index: 27117 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.9764. Min Act: -0.0000

Data Index: 827003 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.8299. Min Act: -0.0000

Data Index: 1254351 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.8163. Min Act: -0.0000

Data Index: 604078 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.8889. Min Act: -0.0000

Data Index: 602492 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.7743. Min Act: -0.0000

Data Index: 1216875 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.8682. Min Act: -0.0000

Data Index: 1232525 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.8867. Min Act: -0.0000

Data Index: 612598 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.7592. Min Act: -0.0000

Data Index: 1069571 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.7822. Min Act: -0.0000

Data Index: 1155731 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.7138. Min Act: -0.0000

Data Index: 840783 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.7187. Min Act: -0.0000

Data Index: 158116 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.7179. Min Act: -0.0000

Data Index: 442753 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.6228. Min Act: -0.0000

Data Index: 277927 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.7139. Min Act: -0.0000

Data Index: 867112 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.6759. Min Act: -0.0000

Data Index: 683734 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.6746. Min Act: -0.0000

Data Index: 1086696 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 2.1982. Min Range: -2.1982

Max Act: 1.5576. Min Act: -0.0000

Data Index: 80743 (C4 (Web Text))

Max Activating Token Index: 535